237 search results - page 30 / 48 » acl 2008 |
ACL
2008
15 years 1 months ago
2008
This paper presents a new unsupervised algorithm (WordEnds) for inferring word boundaries from transcribed adult conversations. Phone ngrams before and after observed pauses are u...
ACL
2008
15 years 1 months ago
2008
In lexicalized grammatical formalisms, it is possible to separate lexical category assignment from the combinatory processes that make use of such categories, such as parsing and ...
107
click to vote
ACL
2008
15 years 1 months ago
2008
Current re-ranking algorithms for machine translation rely on log-linear models, which have the potential problem of underfitting the training data. We present BoostedMERT, a nove...
114
click to vote
ACL
2008
15 years 1 months ago
2008
Word and n-gram posterior probabilities estimated on N-best hypotheses have been used to improve the performance of statistical machine translation (SMT) in a rescoring framework....
49
Voted
ACL
2008
15 years 1 months ago
2008
Frequency counts from very large corpora, such as the Web 1T dataset, have recently become available for language modeling. Omission of low frequency n-gram counts is a practical ...